Natural Language Processing for Surveillance of Cervical and Anal Cancer and Precancer: Algorithm Development and Split-Validation Study

Use of Machine Learning Tools in Evidence Synthesis of Tobacco Use Among Sexual and Gender Diverse Populations: Algorithm Development and Validation

BACKGROUND

From 2016 to 2021, the volume of peer-reviewed publications related to tobacco has experienced a significant increase. This presents a considerable challenge in efficiently summarizing, synthesizing, and disseminating research findings, especially when it comes to addressing specific target populations, such as the LGBTQ+ (lesbian, gay, bisexual, transgender, queer, intersex, asexual, Two Spirit, and other persons who identify as part of this community) populations.

OBJECTIVE

In order to expedite evidence synthesis and research gap discoveries, this pilot study has the following three aims: (1) to compile a specialized semantic database for tobacco policy research to extract information from journal article abstracts, (2) to develop natural language processing (NLP) algorithms that comprehend the literature on nicotine and tobacco product use among sexual and gender diverse populations, and (3) to compare the discoveries of the NLP algorithms with an ongoing systematic review of tobacco policy research among LGBTQ+ populations.

METHODS

We built a tobacco research domain-specific semantic database using data from 2993 paper abstracts from 4 leading tobacco-specific journals, with enrichment from other publicly available sources. We then trained an NLP model to extract named entities after learning patterns and relationships between words and their context in text, which further enriched the semantic database. Using this iterative process, we extracted and assessed studies relevant to LGBTQ+ tobacco control issues, further comparing our findings with an ongoing systematic review that also focuses on evidence synthesis for this demographic group.

RESULTS

In total, 33 studies were identified as relevant to sexual and gender diverse individuals' nicotine and tobacco product use. Consistent with the ongoing systematic review, the NLP results showed that there is a scarcity of studies assessing policy impact on this demographic using causal inference methods. In addition, the literature is dominated by US data. We found that the product drawing the most attention in the body of existing research is cigarettes or cigarette smoking and that the number of studies of various age groups is almost evenly distributed between youth or young adults and adults, consistent with the research needs identified by the US health agencies.

CONCLUSIONS

Our pilot study serves as a compelling demonstration of the capabilities of NLP tools in expediting the processes of evidence synthesis and the identification of research gaps. While future research is needed to statistically test the NLP tool's performance, there is potential for NLP tools to fundamentally transform the approach to evidence synthesis.

Uptake of Cervical Cancer Screening Among Female Patients Using a Mobile Medical Clinic

INTRODUCTION

Although cervical cancer causes morbidity, it can be prevented if diagnosed early; previous research has shown lower rates of screening in patients with health-related social needs by self-report data. This study assessed cervical cancer screening uptake among female patients with health-related social needs who access care through a community-based mobile medical clinic.

METHODS

A retrospective cohort was developed of all cis-female patients aged 21-65 years who sought care at the mobile medical clinic between January 1, 2016 and December 31, 2019, and their medical data were captured from the electronic health record. Bivariate and multivariate logistic regression (performed in 2022/2023) were used to investigate correlates of ever having received cervical cancer screening and of being up to date with cervical cancer screening.

RESULTS

Less than half of the 1,455 patient cohort had ever undergone Pap testing. In the multivariate model, ever having received cervical cancer screening was directly associated with being Hispanic or Black, living with HIV, and having received human papillomavirus vaccination. People who currently smoke showed significantly lower odds of ever having had cervical cancer screening than people who have never smoked. Patients who were single or had other marital status had lower adjusted odds of being up to date as well as those with a substance use history and those with unstable housing.

CONCLUSIONS

Cervical cancer screening rates in this community-based mobile medical clinic model were low, highlighting a need for increased attention to screening in this high-risk population. Mobile medical clinics have increased screening uptake internationally, and this model could be adopted domestically to promote screening to patients who access health care in various settings.

Extracting cancer concepts from clinical notes using natural language processing: a systematic review

BACKGROUND

Extracting information from free texts using natural language processing (NLP) can save time and reduce the hassle of manually extracting large quantities of data from incredibly complex clinical notes of cancer patients. This study aimed to systematically review studies that used NLP methods to identify cancer concepts from clinical notes automatically.

METHODS

PubMed, Scopus, Web of Science, and Embase were searched for English language papers using a combination of the terms concerning "Cancer", "NLP", "Coding", and "Registries" until June 29, 2021. Two reviewers independently assessed the eligibility of papers for inclusion in the review.

RESULTS

Most of the software programs used for concept extraction reported were developed by the researchers (n = 7). Rule-based algorithms were the most frequently used algorithms for developing these programs. In most articles, the criteria of accuracy (n = 14) and sensitivity (n = 12) were used to evaluate the algorithms. In addition, Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) and Unified Medical Language System (UMLS) were the most commonly used terminologies to identify concepts. Most studies focused on breast cancer (n = 4, 19%) and lung cancer (n = 4, 19%).

CONCLUSION

The use of NLP for extracting the concepts and symptoms of cancer has increased in recent years. The rule-based algorithms are well-liked algorithms by developers. Due to these algorithms' high accuracy and sensitivity in identifying and extracting cancer concepts, we suggested that future studies use these algorithms to extract the concepts of other diseases as well.

Computable Clinical Phenotyping of Postacute Sequelae of COVID-19 in Pediatrics Using Real-World Data

Many questions remain unanswered concerning the long-term effects of COVID-19 on children. In this report, we describe a computable phenotyping algorithm for identifying children and adolescents with postacute sequelae of COVID-19 (PASC) and pilot this tool to characterize the clinical epidemiology of pediatric PASC in a large healthcare delivery network.

Natural language processing for clinical notes in dentistry: A systematic review

OBJECTIVE

To identify and synthesise research on applications of natural language processing (NLP) for information extraction and retrieval from clinical notes in dentistry.

MATERIALS AND METHODS

A predefined search strategy was applied in EMBASE, CINAHL and Medline. Studies eligible for inclusion were those that that described, evaluated, or applied NLP to clinical notes containing either human or simulated patient information. Quality of the study design and reporting was independently assessed based on a set of questions derived from relevant tools including CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS). A narrative synthesis was conducted to present the results.

RESULTS

Of the 17 included studies, 10 developed and evaluated NLP methods and 7 described applications of NLP-based information retrieval methods in dental records. Studies were published between 2015 and 2021, most were missing key details needed for reproducibility, and there was no consistency in design or reporting. The 10 studies developing or evaluating NLP methods used document classification or entity extraction, and 4 compared NLP methods to non-NLP methods. The quality of reporting on NLP studies in dentistry has modestly improved over time.

CONCLUSIONS

Study design heterogeneity and incomplete reporting of studies currently limits our ability to synthesise NLP applications in dental records. Standardisation of reporting and improved connections between NLP methods and applied NLP in dentistry may improve how we can make use of clinical notes from dentistry in population health or decision support systems.

PROTOCOL REGISTRATION

PROSPERO CRD42021227823.

An accessible, efficient, and accurate natural language processing method for extracting diagnostic data from pathology reports

Context

Analysis of diagnostic information in pathology reports for the purposes of clinical or translational research and quality assessment/control often requires manual data extraction, which can be laborious, time-consuming, and subject to mistakes.

Objective

We sought to develop, employ, and evaluate a simple, dictionary- and rule-based natural language processing (NLP) algorithm for generating searchable information on various types of parameters from diverse surgical pathology reports.

Design

Data were exported from the pathology laboratory information system (LIS) into extensible markup language (XML) documents, which were parsed by NLP-based Python code into desired data points and delivered to Excel spreadsheets. Accuracy and efficiency were compared to a manual data extraction method with concordance measured by Cohen's κ coefficient and corresponding P values.

Results

The automated method was highly concordant (90%-100%, P<.001) with excellent inter-observer reliability (Cohen's κ: 0.86-1.0) compared to the manual method in 3 clinicopathological research scenarios, including squamous dysplasia presence and grade in anal biopsies, epithelial dysplasia grade and location in colonoscopic surveillance biopsies, and adenocarcinoma grade and amount in prostate core biopsies. Significantly, the automated method was 24-39 times faster and inherently contained links for each diagnosis to additional variables such as patient age, location, etc., which would require additional manual processing time.

Conclusions

A simple, flexible, and scaleable NLP-based platform can be used to correctly, safely, and quickly extract and deliver linked data from pathology reports into searchable spreadsheets for clinical and research purposes.

Natural Language Processing in Pathology: Current Trends and Future Insights

Natural language processing (NLP) plays a key role in advancing health care, being key to extracting structured information from electronic health reports. In the last decade, several advances in the field of pathology have been derived from the application of NLP to pathology reports. Herein, a comprehensive review of the most used NLP methods for extracting, coding, and organizing information from pathology reports is presented, including how the development of tools is used to improve workflow. In addition, this article discusses, from a practical point of view, the steps necessary to extract data and encode natural language information for its analytical processing, ranging from preprocessing of text to its inclusion in complex algorithms. Finally, the potential of NLP-based automatic solutions for improving workflow in pathology and their further applications in the near future is highlighted.

Assessment of Electronic Health Record for Cancer Research and Patient Care Through a Scoping Review of Cancer Natural Language Processing

PURPOSE

The advancement of natural language processing (NLP) has promoted the use of detailed textual data in electronic health records (EHRs) to support cancer research and to facilitate patient care. In this review, we aim to assess EHR for cancer research and patient care by using the Minimal Common Oncology Data Elements (mCODE), which is a community-driven effort to define a minimal set of data elements for cancer research and practice. Specifically, we aim to assess the alignment of NLP-extracted data elements with mCODE and review existing NLP methodologies for extracting said data elements.

METHODS

Published literature studies were searched to retrieve cancer-related NLP articles that were written in English and published between January 2010 and September 2020 from main literature databases. After the retrieval, articles with EHRs as the data source were manually identified. A charting form was developed for relevant study analysis and used to categorize data including four main topics: metadata, EHR data and targeted cancer types, NLP methodology, and oncology data elements and standards.

RESULTS

A total of 123 publications were selected finally and included in our analysis. We found that cancer research and patient care require some data elements beyond mCODE as expected. Transparency and reproductivity are not sufficient in NLP methods, and inconsistency in NLP evaluation exists.

CONCLUSION

We conducted a comprehensive review of cancer NLP for research and patient care using EHRs data. Issues and barriers for wide adoption of cancer NLP were identified and discussed.

Computable Guidelines and Clinical Decision Support for Cervical Cancer Screening and Management to Improve Outcomes and Health Equity

Cervical cancer is highly preventable when precancerous lesions are detected early and appropriately managed. However, the complexity of and frequent updates to existing evidence-based clinical guidelines make it challenging for clinicians to stay abreast of the latest recommendations. In addition, limited availability and accessibility to information technology (IT) decision supports make it difficult for groups who are medically underserved to receive screening or receive the appropriate follow-up care. The Centers for Disease Control and Prevention (CDC), Division of Cancer Prevention and Control (DCPC), is leading a multiyear initiative to develop computer-interpretable ("computable") version of already existing evidence-based guidelines to support clinician awareness and adoption of the most up-to-date cervical cancer screening and management guidelines. DCPC is collaborating with the MITRE Corporation, leading scientists from the National Cancer Institute, and other CDC subject matter experts to translate existing narrative guidelines into computable format and develop clinical decision support tools for integration into health IT systems such as electronic health records with the ultimate goal of improving patient outcomes and decreasing disparities in cervical cancer outcomes among populations that are medically underserved. This initiative meets the challenges and opportunities highlighted by the President's Cancer Panel and the President's Cancer Moonshot 2.0 to nearly eliminate cervical cancer.

Maternal HPV Infection: Effects on Pregnancy Outcome

The human papilloma virus (HPV) infection, caused by a ubiquitous virus typically transmitted through the direct contact of infected organs, either through the skin or mucosa, is the most common sexually transmitted infection, placing young women at a high risk of contracting it. Although the vast majority of cases spontaneously clear within 1-2 years, persistent HPV infection remains a serious concern, as it has repeatedly been linked to the development of multiple malignancies, including cervical, anogenital, and oropharyngeal cancers. Additionally, more recent data suggest a harmful effect of HPV infection on pregnancy. As the maternal hormonal environment and immune system undergo significant changes during pregnancy, the persistence of HPV is arguably favored. Various studies have reported an increased risk of adverse pregnancy outcomes among HPV-positive women, with the clinical impact encompassing a range of conditions, including preterm birth, miscarriage, pregnancy-induced hypertensive disorders (PIHD), intrauterine growth restriction (IUGR), low birth weight, the premature rupture of membranes (PROM), and fetal death. Therefore, understanding the mechanisms employed by HPV that negatively impact pregnancy and assessing potential approaches to counteract them would be of interest in the quest to optimize pregnancy outcomes and improve child survival and health.

Unindicated cervical cancer screening in adolescent females within a large healthcare system in the United States

BACKGROUND

Current consensus recommendations are to not initiate cervical cancer screening for immunocompetent adolescent females before 21 years of age. This is in part because of the very low rate of 0.8 per 100,000 new cervical cancer cases diagnosed among women aged between 20 to 24 years. Timely human papillomavirus vaccination further decreases the incidence of cervical cancer to 4 cases per 100,000 persons by the age of 28 years. Screening before 21 years of age has demonstrated no clear benefit in cancer risk reduction or outcomes. In addition, unindicated screening among adolescents can lead to patient harm and increasing costs to the healthcare system.

OBJECTIVE

It is important to assess the rates of overutilization of cervical cancer screening and to identify areas where improvements have occurred and where further opportunities exist. This study aimed to assess the trends over time and the practice and provider factors associated with unindicated cervical cancer screening tests in adolescent females within the largest healthcare system in the state.

STUDY DESIGN

Cross-sectional data from patients aged 13 to 20 years who underwent cervical cancer screening between January 1, 2012, and December 31, 2018, across a large multihospital health system were reviewed. All cervical cancer screening results were included. The incidence rate of unindicated screening was analyzed over 6-month intervals using the Poisson regression analysis.

RESULTS

The study included data from 118 providers and 794 women. Among the 900 screening results, most (90%) were unindicated: 87% with unindicated cytology testing alone and 14% with unindicated human papillomavirus testing. Screening tests were collected from patients aged 13 to 20 years, many of whom had multiple unindicated cytology tests, with 25 patients having ≥3 tests before the age of 21 years. Most results of cytology testing were negative for intraepithelial lesion or malignancy (77%). Moreover, 52 invasive diagnostic or therapeutic procedures (49 colposcopies and 3 conizations) were performed, of which 45 (87%) followed an unindicated screening test. Between 2012 and 2018, the incidence rate of unindicated cytology decreased by 33% (12.6 to 8.5 unindicated cytology per 1000 encounters). The incidence rate of unindicated screening was lower in the academic setting than in the community setting (incidence rate ratio, 0.43; P<.01). Even with decreases in the overall rates of unindicated screening throughout the study period, there were still 58 unindicated screening tests performed in the final year of this study.

CONCLUSION

Despite substantial reductions in unindicated screening for women aged <21 years, there remained areas for improvement. Our data reflected practices of guideline nonadherence up to 7 years after the 2012 guideline. Now, with a new series of changes to the guidelines, which may be even more challenging for patients and providers, it is more important than ever to utilize evidence-based strategies to improve guideline dissemination and adherence.

College of American Pathologists Cancer Protocols: From Optimizing Cancer Patient Care to Facilitating Interoperable Reporting and Downstream Data Use

The College of American Pathologists Cancer Protocols have offered guidance to pathologists for standard cancer pathology reporting for more than 35 years. The adoption of computer readable versions of these protocols by electronic health record and laboratory information system (LIS) vendors has provided a mechanism for pathologists to report within their LIS workflow, in addition to enabling standardized structured data capture and reporting to downstream consumers of these data such as the cancer surveillance community. This paper reviews the history of the Cancer Protocols and electronic Cancer Checklists, outlines the current use of these critically important cancer case reporting tools, and examines future directions, including plans to help improve the integration of the Cancer Protocols into clinical, public health, research, and other workflows.

Improving broad-coverage medical entity linking with semantic type prediction and large-scale datasets

OBJECTIVES

Biomedical natural language processing tools are increasingly being applied for broad-coverage information extraction-extracting medical information of all types in a scientific document or a clinical note. In such broad-coverage settings, linking mentions of medical concepts to standardized vocabularies requires choosing the best candidate concepts from large inventories covering dozens of types. This study presents a novel semantic type prediction module for biomedical NLP pipelines and two automatically-constructed, large-scale datasets with broad coverage of semantic types.

METHODS

We experiment with five off-the-shelf biomedical NLP toolkits on four benchmark datasets for medical information extraction from scientific literature and clinical notes. All toolkits adopt a staged approach of mention detection followed by two stages of medical entity linking: (1) generating a list of candidate concepts, and (2) picking the best concept among them. We introduce a semantic type prediction module to alleviate the problem of overgeneration of candidate concepts by filtering out irrelevant candidate concepts based on the predicted semantic type of a mention. We present MedType, a fully modular semantic type prediction model which we integrate into the existing NLP toolkits. To address the dearth of broad-coverage training data for medical information extraction, we further present WikiMed and PubMedDS, two large-scale datasets for medical entity linking.

RESULTS

Semantic type filtering improves medical entity linking performance across all toolkits and datasets, often by several percentage points of F-1. Further, pretraining MedType on our novel datasets achieves state-of-the-art performance for semantic type prediction in biomedical text.

CONCLUSIONS

Semantic type prediction is a key part of building accurate NLP pipelines for broad-coverage information extraction from biomedical text. We make our source code and novel datasets publicly available to foster reproducible research.

Clinical Natural Language Processing for Radiation Oncology: A Review and Practical Primer

Natural language processing (NLP), which aims to convert human language into expressions that can be analyzed by computers, is one of the most rapidly developing and widely used technologies in the field of artificial intelligence. Natural language processing algorithms convert unstructured free text data into structured data that can be extracted and analyzed at scale. In medicine, this unlocking of the rich, expressive data within clinical free text in electronic medical records will help untap the full potential of big data for research and clinical purposes. Recent major NLP algorithmic advances have significantly improved the performance of these algorithms, leading to a surge in academic and industry interest in developing tools to automate information extraction and phenotyping from clinical texts. Thus, these technologies are poised to transform medical research and alter clinical practices in the future. Radiation oncology stands to benefit from NLP algorithms if they are appropriately developed and deployed, as they may enable advances such as automated inclusion of radiation therapy details into cancer registries, discovery of novel insights about cancer care, and improved patient data curation and presentation at the point of care. However, challenges remain before the full value of NLP is realized, such as the plethora of jargon specific to radiation oncology, nonstandard nomenclature, a lack of publicly available labeled data for model development, and interoperability limitations between radiation oncology data silos. Successful development and implementation of high quality and high value NLP models for radiation oncology will require close collaboration between computer scientists and the radiation oncology community. Here, we present a primer on artificial intelligence algorithms in general and NLP algorithms in particular; provide guidance on how to assess the performance of such algorithms; review prior research on NLP algorithms for oncology; and describe future avenues for NLP in radiation oncology research and clinics.